x86/speculation/l1tf: Protect swap entries against L1TF
authorLinus Torvalds <torvalds@linux-foundation.org>
Wed, 13 Jun 2018 22:48:23 +0000 (15:48 -0700)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 15 Aug 2018 16:12:50 +0000 (18:12 +0200)
commit83ef7e8c0cb72510588ee8b96f5cf30c1ecd9270
treee0e27e9c17710d02feba9f9c5edfee61de495ea4
parent39991a7aa8d527164a87f90bb18b07b2699ed7d0
x86/speculation/l1tf: Protect swap entries against L1TF

commit 2f22b4cd45b67b3496f4aa4c7180a1271c6452f6 upstream

With L1 terminal fault the CPU speculates into unmapped PTEs, and resulting
side effects allow to read the memory the PTE is pointing too, if its
values are still in the L1 cache.

For swapped out pages Linux uses unmapped PTEs and stores a swap entry into
them.

To protect against L1TF it must be ensured that the swap entry is not
pointing to valid memory, which requires setting higher bits (between bit
36 and bit 45) that are inside the CPUs physical address space, but outside
any real memory.

To do this invert the offset to make sure the higher bits are always set,
as long as the swap file is not too big.

Note there is no workaround for 32bit !PAE, or on systems which have more
than MAX_PA/2 worth of memory. The later case is very unlikely to happen on
real systems.

[AK: updated description and minor tweaks by. Split out from the original
     patch ]

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
arch/x86/include/asm/pgtable_64.h